Related papers: BRepFormer: Transformer-Based B-rep Geometric Feat…

The recent rise of generative artificial intelligence (AI), powered by Transformer networks, has achieved remarkable success in natural language processing, computer vision, and graphics. However, the application of Transformers in…

Blind face restoration is a challenging task due to the unknown and complex degradation. Although face prior-based methods and reference-based methods have recently demonstrated high-quality results, the restored images tend to contain…

Boundary representation (B-rep) is the industry standard for computer-aided design (CAD). While deep learning shows promise in processing B-rep models, existing methods suffer from a representation gap: continuous approaches offer…

This paper presents a novel geometric representation for CAD Boundary Representation (B-Rep) based on volumetric distance functions, dubbed B-Rep Distance Functions (BR-DF). BR-DF encodes the surface mesh geometry of a CAD model as signed…

Feature pyramids have been widely adopted in convolutional neural networks and transformers for tasks in medical image segmentation. However, existing models generally focus on the Encoder-side Transformer for feature extraction. We further…

We propose a masked self-supervised learning framework, called BRepMAE, for automatically extracting a valuable representation of the input computer-aided design (CAD) model to recognize its machining features. Representation learning is…

We present PBFormer, an efficient yet powerful scene text detector that unifies the transformer with a novel text shape representation Polynomial Band (PB). The representation has four polynomial curves to fit a text's top, bottom, left,…

Graph-based machine learning has emerged as a promising approach for manufacturability analysis by learning directly from CAD models represented as Boundary Representations (B-reps), exploiting both surface geometry and topological…

Boundary representation (B-rep) models are the standard way 3D shapes are described in Computer-Aided Design (CAD) applications. They combine lightweight parametric curves and surfaces with topological information which connects the…

Boundary representation (B-rep) is the de facto standard for modern CAD, yet learning-based B-rep synthesis remains challenging due to the tight coupling between discrete topology and continuous geometry. We observe a fundamental asymmetry…

Boundary representation (B-rep) of geometric models is a fundamental format in Computer-Aided Design (CAD). However, automatically generating valid and high-quality B-rep models remains challenging due to the complex interdependence between…

We introduce a novel self-supervised learning framework that automatically learns representations from input computer-aided design (CAD) models for downstream tasks, including part classification, modeling segmentation, and machining…

Blind face restoration (BFR) has attracted increasing attention with the rise of generative methods. Most existing approaches integrate generative priors into the restoration pro- cess, aiming to jointly address facial detail generation and…

This paper presents a Refinement Pyramid Transformer (RePFormer) for robust facial landmark detection. Most facial landmark detectors focus on learning representative image features. However, these CNN-based feature representations are not…

Ptychography is a computational method of microscopy that recovers high-resolution transmission images of samples from a series of diffraction patterns. While conventional phase retrieval algorithms can iteratively recover the images, they…

Pedestrian attribute recognition (PAR) has received increasing attention because of its wide application in video surveillance and pedestrian analysis. Extracting robust feature representation is one of the key challenges in this task. The…

We tackle the problem of automatically reconstructing a complete 3D model of a scene from a single RGB image. This challenging task requires inferring the shape of both visible and occluded surfaces. Our approach utilizes viewer-centered,…

The boundary representation (B-Rep) is the standard data structure used in Computer-Aided Design (CAD) for defining solid models. Despite recent progress, directly generating B-Reps end-to-end with precise geometry and watertight topology…

This paper presents ViewFormer, a simple yet effective model for multi-view 3d shape recognition and retrieval. We systematically investigate the existing methods for aggregating multi-view information and propose a novel ``view set"…

Local feature matching between images remains a challenging task, especially in the presence of significant appearance variations, e.g., extreme viewpoint changes. In this work, we propose DeepMatcher, a deep Transformer-based network built…